Update README.md

README.md

@@ -24,6 +24,8 @@ language:
 ![Liquid AI](https://img.shields.io/badge/Architecture-Liquid%20Neural%20Network-cyan?style=for-the-badge)
 ![Function Calling](https://img.shields.io/badge/Task-SOTA%20Function%20Calling-orange?style=for-the-badge)
 ![Size](https://img.shields.io/badge/Params-1.2B-green?style=for-the-badge)
+[![GGUF Available](https://img.shields.io/badge/GGUF-Standard-yellow?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/mradermacher/LFM2.5-1.2B-Nova-Function-Calling-GGUF)
+[![Imatrix GGUF Available](https://img.shields.io/badge/GGUF-Imatrix_(High_Quality)-orange?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/mradermacher/LFM2.5-1.2B-Nova-Function-Calling-i1-GGUF)
 
 </div>
 
@@ -94,11 +96,14 @@ Expected Output:
 </tool_call>
 ```
 
-### 2. Using GGUF (llama.cpp / Ollama)
-This model is available in GGUF format in the companion repository: NovachronoAI/LFM2.5-1.2B-Nova-Function-Calling-GGUF
- * Recommended: q4_k_m.gguf (Balanced Speed/Quality - ~800MB)
- * Max Quality: f16.gguf (Lossless - ~2.5GB)
- * Max Speed: q2_k.gguf (Extreme Speed - ~400MB)
+## 📥 Download GGUF (Quantized)
+Thanks to **[mradermacher](https://huggingface.co/mradermacher)**, this model is available in high-performance GGUF formats for local inference (llama.cpp, Ollama, LM Studio).
+
+| Version | Description | Recommended For | Link |
+| :--- | :--- | :--- | :--- |
+| **Standard GGUF** | Traditional static quantization. | General testing & broad compatibility. | [**Download**](https://huggingface.co/mradermacher/LFM2.5-1.2B-Nova-Function-Calling-GGUF) |
+| **Imatrix GGUF** | **(Best Quality)** Importance Matrix tuned. Higher accuracy at small sizes. | **Low VRAM** devices (Android/Pi) or max quality needs. | [**Download**](https://huggingface.co/mradermacher/LFM2.5-1.2B-Nova-Function-Calling-i1-GGUF) |
+
 ### ⚙️ Training Details
 | Parameter | Value |
 |---|---|